llm gateway Saas
10035521 Canada Inc · Software Development
Certification per Microsoft Marketplace.
Evidence tier Source Confirmed · 7 captures on record
What the publisher says
As described on Microsoft Marketplace.
LLM Gateway SaaS is a high-performance solution designed to unify access to large language models (LLMs) for enterprises and developers. This Software-as-a-Service platform streamlines the integration of advanced AI capabilities, reducing costs and simplifying workflows for users.
Ideal for businesses and developers aiming to leverage AI for tasks such as natural language processing, content creation, and data analysis, LLM Gateway SaaS provides flexibility, scalability, and reliability. It enables users to focus on innovation while the platform efficiently manages model access and infrastructure.
Show the rest of the publisher’s description (54 more lines)
By addressing common challenges like cost management and technical complexity, LLM Gateway SaaS makes cutting-edge AI accessible to organizations of all sizes. This solution is perfect for accelerating AI-driven projects and enhancing operational efficiency.
LLM Gateway — Features
Core Inference
- Chat Completions (`/v1/chat/completions`) — OpenAI-compatible proxy to any provider
- Embeddings (`/v1/embeddings`) — Embedding generation via any enabled provider
- Model Discovery (`/v1/models`) — Unified model list across all active providers
- Agentic AI (`/v1/agent/run`) — Plan→Execute→Synthesize loop with gateway-native tool calls
Provider Management
- Provider CRUD — Add/update/delete providers (OpenAI, Azure, Anthropic, Ollama, etc.)
- API Key Pool — Multiple keys per provider, load-balanced automatically
- Provider Health — Live health status per provider
- Encryption at Rest — AES-256-GCM for all stored API keys and Redis passwords
Routing
- LLM Routes — Named sluggable routes binding model, provider, system prompt, temperature
- Failover Routing — Per-route fallback provider list tried on failure
- Circuit Breaker — Auto-opens after consecutive failures, auto-recovers
- JSON Schema Enforcement — Validate model output against a per-route output schema
Prompt Management
- Prompt Templates — Reusable versioned prompt templates
- Prompt Testing — Test a prompt version against a live model live
Caching
- Semantic Cache — Redis-backed response cache, configurable per user
API Key Management
- Gateway Keys — Scoped keys with prefix, expiry, allowed providers/models
- Key Groups — Group keys for policy and analytics segmentation
Cost Tracking
- Cost Config — Per-model token pricing (input/output per 1M tokens)
- Cost Breakdown — Spend analytics by model, provider, or user
Analytics & Observability
- Request Log — Full per-request log: tokens, latency, model, cost
- Usage Metrics — Aggregated token and cost totals
- Observability — Latency percentiles, error rates, throughput
- Audit Log — Immutable trail of all management-plane changes
- OpenTelemetry — Distributed tracing exported via OTLP
Plans & Licensing
- Basic Plan — 5M tokens/month cap; HTTP 429 on breach
- Professional Plan — Unlimited tokens; activated via license key
- License UI — Admin activates key in dashboard; shows plan badge + token usage
- Per-user Plans — Admin assigns plans to individual users
User & Auth
- JWT Auth — Signed JWT on login; enforced on all management routes
- API Key Auth — Inference endpoints accept `X-API-Key` header
- Role-based Access — Admin role required for providers, routes, user management
Security
- SSRF Protection — Outbound URLs validated against private CIDR blocklist
- Rate Limiting — Configurable auth (default 20/min) and API (default 120/min) limits
- Security Headers — HSTS, X-Frame-Options, X-Content-Type-Options on all responses
- Request Body Limit — 10 MiB global cap on all incoming requests
- Provider Header Denylist — Strips Set-Cookie, WWW-Authenticate, CORS headers from provider responses
Agentic Tools
- `query_usage_analytics` — Agent reads current plan, used & remaining tokens
- `list_routes` — Agent enumerates all configured .
Contact :+1 4376034536
email: pv@realtimedetect.com
Preview
4 images
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment
Sources
Publisher resources
1 linkLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.